style-transfer-paraphrase

style-transfer-paraphrase copied to clipboard

Add example scripts for training CDS models

11

Additionally, add `dict.txt` files for these dataset folders

martiansideofthemoon

RuntimeError: probability tensor contains either inf, nan or element < 0

2

Hi! I have finetuned inverse paraphraser on custom dataset. Model has been saved. Now I am trying to load this model by running demo_paraphraser.py but it's giving `RuntimeError: probability tensor...

HassanBinAli

Perplexity value during training remains constant

1

When i train on the Shakespeare data, for both shakespeare_0 or shakespeare_1, the perplexity value in eval_results remins constant perplexity= tensor(135.8836) Although the model trains till checkpoint=13797 , the quality...

Yaffa16

martiansideofthemoon

Error when using multiple GPUs

1

Thank you for the awesome and interesting research and project. I was wondering if anyone has encountered the following error when using multiple gpu. I have 4 Titan V gpus...

eomiso

Thanks to Anubhav Jangra for reporting this --- Email #1 I am unable to replicate the fluency and style accuracy scores. Here are a few numbers I'm getting right now...

martiansideofthemoon

HuggingFace Outputs

1

Hello, Thanks for sharing your awesome research and codes. Would you mind sharing some details on how to use the huggingFace models? I'm using generate API on some examples but...

erfan226

Thanks to Anubhav Jangra for reporting these, ``` Issue #2 (datasets/bpe2text.py) Running the file I got the following error: Downloading: "https://github.com/pytorch/fairseq/archive/master.zip" to /home/anubhavjangra/.cache/torch/hub/master.zip Traceback (most recent call last): File "bpe2text.py",...

martiansideofthemoon

Cross-posting here to keep track of issues related to two-step pipelined generation & usage of HuggingFace APIs --- https://github.com/GEM-benchmark/NL-Augmenter/issues/298

martiansideofthemoon

Failure to create the BPE dataset for custom dataset

6

Hi I am trying to train a style transfer model for a style (i.e., profane vs. civil) that is not supported in the paper. However, when I tried to run...

guanqun-yang